From: Huang Ying <ying.hu...@intel.com>

With this patch, a THP (Transparent Huge Page) can be added/deleted
to/from the swap cache as a set of (HPAGE_PMD_NR) sub-pages.

This will be used for the THP (Transparent Huge Page) swap support.
Where one THP may be added/delted to/from the swap cache.  This will
batch the swap cache operations to reduce the lock acquire/release times
for the THP swap too.

Cc: Hugh Dickins <hu...@google.com>
Cc: Shaohua Li <s...@kernel.org>
Cc: Minchan Kim <minc...@kernel.org>
Cc: Rik van Riel <r...@redhat.com>
Cc: Andrea Arcangeli <aarca...@redhat.com>
Cc: Kirill A. Shutemov <kirill.shute...@linux.intel.com>
Signed-off-by: "Huang, Ying" <ying.hu...@intel.com>
---
 include/linux/page-flags.h |  5 ++--
 mm/swap_state.c            | 64 ++++++++++++++++++++++++++++++----------------
 2 files changed, 45 insertions(+), 24 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6b5818d6de32..f4acd6c4f808 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -326,11 +326,12 @@ PAGEFLAG_FALSE(HighMem)
 #ifdef CONFIG_SWAP
 static __always_inline int PageSwapCache(struct page *page)
 {
+       page = compound_head(page);
        return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags);
 
 }
-SETPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
-CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
+SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
+CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 199a07efc44d..504f67d73f67 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -38,6 +38,7 @@ struct address_space *swapper_spaces[MAX_SWAPFILES];
 static unsigned int nr_swapper_spaces[MAX_SWAPFILES];
 
 #define INC_CACHE_INFO(x)      do { swap_cache_info.x++; } while (0)
+#define ADD_CACHE_INFO(x, nr)  do { swap_cache_info.x += (nr); } while (0)
 
 static struct {
        unsigned long add_total;
@@ -90,39 +91,52 @@ void show_swap_cache_info(void)
  */
 int __add_to_swap_cache(struct page *page, swp_entry_t entry)
 {
-       int error;
+       int error, i, nr = hpage_nr_pages(page);
        struct address_space *address_space;
+       struct page *cur_page;
+       swp_entry_t cur_entry;
 
        VM_BUG_ON_PAGE(!PageLocked(page), page);
        VM_BUG_ON_PAGE(PageSwapCache(page), page);
        VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
 
-       get_page(page);
+       page_ref_add(page, nr);
        SetPageSwapCache(page);
-       set_page_private(page, entry.val);
 
        address_space = swap_address_space(entry);
+       cur_page = page;
+       cur_entry.val = entry.val;
        spin_lock_irq(&address_space->tree_lock);
-       error = radix_tree_insert(&address_space->page_tree,
-                                 swp_offset(entry), page);
-       if (likely(!error)) {
-               address_space->nrpages++;
-               __inc_node_page_state(page, NR_FILE_PAGES);
-               INC_CACHE_INFO(add_total);
+       for (i = 0; i < nr; i++, cur_page++, cur_entry.val++) {
+               set_page_private(cur_page, cur_entry.val);
+               error = radix_tree_insert(&address_space->page_tree,
+                                         swp_offset(cur_entry), cur_page);
+               if (unlikely(error))
+                       break;
        }
-       spin_unlock_irq(&address_space->tree_lock);
-
-       if (unlikely(error)) {
+       if (likely(!error)) {
+               address_space->nrpages += nr;
+               __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
+               ADD_CACHE_INFO(add_total, nr);
+       } else {
                /*
                 * Only the context which have set SWAP_HAS_CACHE flag
                 * would call add_to_swap_cache().
                 * So add_to_swap_cache() doesn't returns -EEXIST.
                 */
                VM_BUG_ON(error == -EEXIST);
-               set_page_private(page, 0UL);
+               set_page_private(cur_page, 0UL);
+               while (i--) {
+                       cur_page--;
+                       cur_entry.val--;
+                       radix_tree_delete(&address_space->page_tree,
+                                         swp_offset(cur_entry));
+                       set_page_private(cur_page, 0UL);
+               }
                ClearPageSwapCache(page);
-               put_page(page);
+               page_ref_sub(page, nr);
        }
+       spin_unlock_irq(&address_space->tree_lock);
 
        return error;
 }
@@ -132,7 +146,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, 
gfp_t gfp_mask)
 {
        int error;
 
-       error = radix_tree_maybe_preload(gfp_mask);
+       error = radix_tree_maybe_preload_order(gfp_mask, compound_order(page));
        if (!error) {
                error = __add_to_swap_cache(page, entry);
                radix_tree_preload_end();
@@ -148,6 +162,7 @@ void __delete_from_swap_cache(struct page *page)
 {
        swp_entry_t entry;
        struct address_space *address_space;
+       int i, nr = hpage_nr_pages(page);
 
        VM_BUG_ON_PAGE(!PageLocked(page), page);
        VM_BUG_ON_PAGE(!PageSwapCache(page), page);
@@ -155,12 +170,17 @@ void __delete_from_swap_cache(struct page *page)
 
        entry.val = page_private(page);
        address_space = swap_address_space(entry);
-       radix_tree_delete(&address_space->page_tree, swp_offset(entry));
-       set_page_private(page, 0);
+       for (i = 0; i < nr; i++, entry.val++) {
+               struct page *cur_page = page + i;
+
+               radix_tree_delete(&address_space->page_tree,
+                                 swp_offset(entry));
+               set_page_private(cur_page, 0);
+       }
        ClearPageSwapCache(page);
-       address_space->nrpages--;
-       __dec_node_page_state(page, NR_FILE_PAGES);
-       INC_CACHE_INFO(del_total);
+       address_space->nrpages -= nr;
+       __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
+       ADD_CACHE_INFO(del_total, nr);
 }
 
 /**
@@ -237,8 +257,8 @@ void delete_from_swap_cache(struct page *page)
        __delete_from_swap_cache(page);
        spin_unlock_irq(&address_space->tree_lock);
 
-       swapcache_free(entry);
-       put_page(page);
+       __swapcache_free(entry, PageTransHuge(page));
+       page_ref_sub(page, hpage_nr_pages(page));
 }
 
 /* 
-- 
2.11.0

Reply via email to